Directory
Published directory entries matching your search.
An online tool that removes video backgrounds using AI, accepting MP4, MOV and WEBM files. Free exports are 720p MP4 with a light watermark, while Pro allows 4K export without a watermark. Files are auto-deleted within one hour and are not used for training.
Video Generation Leaderboard is a Hugging Face Space created by ArtificialAnalysis. It displays a live leaderboard of text-to-video and image-to-video models, allowing users to browse sample videos generated from text prompts and view model rankings.
Voice-Swap is an AI voice platform for musicians, content creators, and artists. It offers a text-to-speech voiceover studio, a singing studio for voice swapping and stem separation, and custom voice model training. The site states that voice modelling, generation and rights management are combined into a single system.
VSCO is a photography platform offering photo and video editing tools, film-inspired presets, an AI photo editor, and a community for photographers. It also provides business tools including client galleries, studio management, and portfolio sites. The service is available as a mobile app for iOS and Android and as a desktop web app.
Wan is an AI creative platform. It aims to lower the barrier to creative work using artificial intelligence. The site lists features including text-to-image, image-to-image, text-to-video, image-to-video and image editing.
A Gary Marcus article on his Marcus on AI Substack asking when the GenAI bubble might burst and how that could happen within 12 months. It cites survey findings on generative AI and security, notes $50B in and $3B out, and argues that hallucinations remain and that the industry is built on hype.
Generate mind maps, flowcharts, sequence diagrams, and more from a simple text prompt with Whimsical AI. Get started for free.
An essay by Arjun Ramani and Zhengdong Wang arguing that transformative AI is hard to achieve, assembling technical, social and economic arguments. It notes that trend growth of GDP per capita in frontier economies has never exceeded three percent per year, and that major technical hurdles remain despite rapid progress in some subfields.
A blog post explaining why upscaling AI-generated images matters in image-to-image workflows. It describes how diffusion models apply and remove noise, and how higher-resolution reference images give the model more defined details. The post compares a low-resolution and upscaled example using Stable Diffusion's ControlNet with the canny model, and mentions upscaling options including ImgUpscaler, TopazLabs and Upscale Media.
Word-As-Image for Semantic Typography is a research method that automatically creates word-as-image illustrations, visualizing a word's meaning while preserving readability. It optimizes letter outlines guided by a pretrained Stable Diffusion model and handles a large variety of semantic concepts and any font.
Zoo is a web guide or update reference covering changes, screenshots, notices, or community notes.
